Python: Adds sample documentation for two separate Neo4j context providers for retrieval and memory

Author: retroryan

agent-framework/user-guide/agents/TOC.yml

@@ -8,8 +8,8 @@
   href: agent-memory.md
 - name: Agent Tools
   href: agent-tools.md
-- name: Agent Retrieval Augmented Generation (RAG)
-  href: agent-rag.md
+- name: Agent GraphRAG
+  href: agent-graphrag.md
 - name: Agent Middleware
   href: agent-middleware.md
 - name: Agent Background Responses

…framework/user-guide/agents/agent-rag.md …work/user-guide/agents/agent-graphrag.mdagent-framework/user-guide/agents/agent-rag.md renamed to agent-framework/user-guide/agents/agent-graphrag.md agent-framework/user-guide/agents/agent-rag.md renamed to agent-framework/user-guide/agents/agent-graphrag.md

@@ -1,6 +1,6 @@
 ---
-title: Agent Retrieval Augmented Generation (RAG)
-description: Learn how to use Retrieval Augmented Generation (RAG) with Agent Framework
+title: Agent GraphRAG
+description: Learn how to use GraphRAG with Agent Framework
 zone_pivot_groups: programming-languages
 author: westey-m
 ms.topic: reference
@@ -9,17 +9,17 @@ ms.date: 11/11/2025
 ms.service: agent-framework
 ---
 
-# Agent Retrieval Augmented Generation (RAG)
+# Agent GraphRAG
 
-Microsoft Agent Framework supports adding Retrieval Augmented Generation (RAG) capabilities to agents easily by adding AI Context Providers to the agent.
+Microsoft Agent Framework supports adding GraphRAG capabilities to agents easily by adding AI Context Providers to the agent.
 
 ::: zone pivot="programming-language-csharp"
 
 ## Using TextSearchProvider
 
-The `TextSearchProvider` class is an out-of-the-box implementation of a RAG context provider.
+The `TextSearchProvider` class is an out-of-the-box implementation of a GraphRAG context provider.
 
-It can easily be attached to a `ChatClientAgent` using the `AIContextProviderFactory` option to provide RAG capabilities to the agent.
+It can easily be attached to a `ChatClientAgent` using the `AIContextProviderFactory` option to provide GraphRAG capabilities to the agent.
 
 The factory is an async function that receives a context object and a cancellation token.
 
@@ -92,7 +92,7 @@ The `TextSearchProvider` class supports the following options via the `TextSearc
 
 ## Using Semantic Kernel VectorStore with Agent Framework
 
-Agent Framework supports using Semantic Kernel's VectorStore collections to provide RAG capabilities to agents. This is achieved through the bridge functionality that converts Semantic Kernel search functions into Agent Framework tools.
+Agent Framework supports using Semantic Kernel's VectorStore collections to provide GraphRAG capabilities to agents. This is achieved through the bridge functionality that converts Semantic Kernel search functions into Agent Framework tools.
 
 > [!IMPORTANT]
 > This feature requires `semantic-kernel` version 1.38 or higher.
@@ -160,7 +160,7 @@ async with collection:
         tools=search_tool
     )
 
-    # Use the agent with RAG capabilities
+    # Use the agent with GraphRAG capabilities
     response = await agent.run("How do I return a product?")
     print(response.text)
 ```
@@ -295,6 +295,57 @@ This pattern works with any Semantic Kernel VectorStore connector, including:
 
 Each connector provides the same `create_search_function` method that can be bridged to Agent Framework tools, allowing you to choose the vector database that best fits your needs. See [the full list here](/semantic-kernel/concepts/vector-store-connectors/out-of-the-box-connectors).
 
+### Using Neo4j for GraphRAG
+
+Neo4j offers two separate integrations for Agent Framework, each serving a different purpose. This provider (`agent-framework-neo4j`) is for **GraphRAG** — searching an existing knowledge graph to ground agent responses. For **persistent memory** that learns from conversations and builds a knowledge graph over time, see the [Neo4j Memory Provider](./agent-memory.md#neo4j-memory-provider).
+
+For knowledge graph scenarios where relationships between entities matter, the Neo4j Context Provider offers GraphRAG. It supports vector, fulltext, and hybrid search modes, with optional graph traversal to enrich results with related entities via custom Cypher queries.
+
+```python
+from agent_framework import Agent
+from agent_framework.azure import AzureAIClient
+from agent_framework_neo4j import Neo4jContextProvider, Neo4jSettings, AzureAIEmbedder
+from azure.identity.aio import AzureCliCredential
+
+settings = Neo4jSettings()
+
+neo4j_provider = Neo4jContextProvider(
+    uri=settings.uri,
+    username=settings.username,
+    password=settings.get_password(),
+    index_name="documentChunks",
+    index_type="vector",
+    embedder=AzureAIEmbedder(...),
+    top_k=5,
+    retrieval_query="""
+        MATCH (node)-[:FROM_DOCUMENT]->(doc:Document)
+        OPTIONAL MATCH (doc)<-[:FILED]-(company:Company)
+        RETURN node.text AS text, score, doc.title AS title, company.name AS company
+        ORDER BY score DESC
+    """,
+)
+
+async with (
+    neo4j_provider,
+    AzureAIClient(credential=AzureCliCredential(), project_endpoint=project_endpoint) as client,
+    Agent(
+        client=client,
+        instructions="You are a financial analyst assistant.",
+        context_providers=[neo4j_provider],
+    ) as agent,
+):
+    session = agent.create_session()
+    response = await agent.run("What risks does Acme Corp face?", session=session)
+```
+
+Key features:
+- **Index-driven**: Works with any Neo4j vector or fulltext index
+- **Graph traversal**: Custom Cypher queries enrich search results with related entities
+- **Search modes**: Vector (semantic similarity), fulltext (keyword/BM25), or hybrid (both combined)
+
+> [!TIP]
+> Install with `pip install agent-framework-neo4j`. See the [Neo4j Context Provider repository](https://github.com/neo4j-labs/neo4j-maf-provider) for complete documentation.
+
 ::: zone-end
 
 ## Next steps

agent-framework/user-guide/agents/agent-memory.md

@@ -329,6 +329,59 @@ agent = ChatAgent(
 )
 ```
 
+#### Neo4j Memory Provider
+
+Neo4j offers two separate integrations for Agent Framework, each serving a different purpose. This provider (`neo4j-agent-memory`) is for **persistent memory** — storing and recalling agent interactions, extracting entities, and building a knowledge graph over time. For **GraphRAG** from an existing knowledge graph using vector, fulltext, or hybrid search, see the [Neo4j Context Provider for GraphRAG](./agent-graphrag.md#using-neo4j-for-graphrag).
+
+The Neo4j Memory Provider gives agents persistent memory backed by a knowledge graph. Unlike GraphRAG providers that retrieve from static knowledge bases, the memory provider stores and recalls agent interactions, automatically extracting entities and building a knowledge graph over time.
+
+The provider manages three types of memory:
+- **Short-term memory**: Conversation history and recent context
+- **Long-term memory**: Entities, preferences, and facts extracted from interactions
+- **Reasoning memory**: Past reasoning traces and tool usage patterns
+
+```python
+from agent_framework import Agent
+from agent_framework.azure import AzureAIClient
+from azure.identity.aio import AzureCliCredential
+from neo4j_agent_memory import MemoryClient, MemorySettings
+from neo4j_agent_memory.integrations.microsoft_agent import (
+    Neo4jMicrosoftMemory,
+    create_memory_tools,
+)
+
+settings = MemorySettings()
+memory_client = MemoryClient(settings)
+
+async with memory_client:
+    memory = Neo4jMicrosoftMemory.from_memory_client(
+        memory_client=memory_client,
+        session_id="user-123",
+    )
+    tools = create_memory_tools(memory)
+
+    async with (
+        AzureAIClient(credential=AzureCliCredential(), project_endpoint=project_endpoint) as client,
+        Agent(
+            client=client,
+            instructions="You are a helpful assistant with persistent memory.",
+            tools=tools,
+            context_providers=[memory.context_provider],
+        ) as agent,
+    ):
+        session = agent.create_session()
+        response = await agent.run("Remember that I prefer window seats on flights.", session=session)
+```
+
+Key features:
+- **Bidirectional**: Automatically retrieves relevant context before invocation and saves new memories after responses
+- **Entity extraction**: Builds a knowledge graph from conversations using a multi-stage extraction pipeline
+- **Preference learning**: Infers and stores user preferences across sessions
+- **Memory tools**: Agents can explicitly search memory, remember preferences, and find entity connections
+
+> [!TIP]
+> Install with `pip install neo4j-agent-memory[microsoft-agent]`. See the [Neo4j Agent Memory repository](https://github.com/neo4j-labs/agent-memory) for complete documentation.
+
 ### Thread Serialization and Persistence
 The framework supports serializing entire thread states for persistence across application restarts:
 

agent-framework/user-guide/agents/agent-tools.md

@@ -292,4 +292,4 @@ result = await agent.run(
 ## Next steps
 
 > [!div class="nextstepaction"]
-> [Agent Retrieval Augmented Generation](./agent-rag.md)
+> [Agent GraphRAG](./agent-graphrag.md)

semantic-kernel/Frameworks/agent/TOC.yml

@@ -14,8 +14,8 @@
   href: agent-streaming.md
 - name: Agent Memory
   href: agent-memory.md
-- name: Agent Text Search (RAG)
-  href: agent-rag.md
+- name: Agent GraphRAG
+  href: agent-graphrag.md
 - name: Supported Agent Types
   href: agent-types/TOC.yml
 - name: Agent Orchestration

…tic-kernel/Frameworks/agent/agent-rag.md …ernel/Frameworks/agent/agent-graphrag.mdsemantic-kernel/Frameworks/agent/agent-rag.md renamed to semantic-kernel/Frameworks/agent/agent-graphrag.md semantic-kernel/Frameworks/agent/agent-rag.md renamed to semantic-kernel/Frameworks/agent/agent-graphrag.md

@@ -1,6 +1,6 @@
 ---
-title: Adding Retrieval Augmented Generation (RAG) to Semantic Kernel Agents
-description: How to use the TextSearchProvider for Retrieval Augmented Generation (RAG) with Semantic Kernel Agents
+title: Adding GraphRAG to Semantic Kernel Agents
+description: How to use the TextSearchProvider for GraphRAG with Semantic Kernel Agents
 zone_pivot_groups: programming-languages
 author: westey-m
 ms.topic: conceptual
@@ -9,14 +9,14 @@ ms.date: 05/22/2025
 ms.service: semantic-kernel
 ---
 
-# Adding Retrieval Augmented Generation (RAG) to Semantic Kernel Agents
+# Adding GraphRAG to Semantic Kernel Agents
 
 ::: zone pivot="programming-language-csharp"
 
 > [!WARNING]
-> The Semantic Kernel Agent RAG functionality is experimental, subject to change, and will only be finalized based on feedback and evaluation.
+> The Semantic Kernel Agent GraphRAG functionality is experimental, subject to change, and will only be finalized based on feedback and evaluation.
 
-## Using the TextSearchProvider for RAG
+## Using the TextSearchProvider for GraphRAG
 
 The `Microsoft.SemanticKernel.Data.TextSearchProvider` allows agents to retrieve relevant documents based on user input and inject them into the agent's context for more informed responses.
 It integrates an `Microsoft.SemanticKernel.Data.ITextSearch` instance with Semantic Kernel agents.
@@ -30,7 +30,7 @@ We also provide a `Microsoft.SemanticKernel.Data.TextSearchStore`, which provide
 
 The `TextSearchProvider` can be used with a `VectorStore` and `TextSearchStore` to store and search text documents.
 
-The following example demonstrates how to set up and use the `TextSearchProvider` with a `TextSearchStore` and `InMemoryVectorStore` for an agent to perform simple RAG over text.
+The following example demonstrates how to set up and use the `TextSearchProvider` with a `TextSearchStore` and `InMemoryVectorStore` for an agent to perform simple GraphRAG over text.
 
 ```csharp
 // Create an embedding generator using Azure OpenAI.
@@ -58,7 +58,7 @@ ChatCompletionAgent agent = new()
     Name = "FriendlyAssistant",
     Instructions = "You are a friendly assistant",
     Kernel = kernel,
-    // This setting must be set to true when using the on-demand RAG feature
+    // This setting must be set to true when using the on-demand GraphRAG feature
     UseImmutableKernel = true
 };
 
@@ -67,7 +67,7 @@ ChatHistoryAgentThread agentThread = new();
 var textSearchProvider = new TextSearchProvider(textSearchStore);
 agentThread.AIContextProviders.Add(textSearchProvider);
 
-// Use the agent with RAG capabilities.
+// Use the agent with GraphRAG capabilities.
 ChatMessageContent response = await agent.InvokeAsync("Where is Contoso based?", agentThread).FirstAsync();
 Console.WriteLine(response.Content);
 ```
@@ -110,7 +110,7 @@ using var textSearchStore = new TextSearchStore<string>(
 );
 ```
 
-### Automatic vs on-demand RAG
+### Automatic vs on-demand GraphRAG
 
 The `TextSearchProvider` can perform searches automatically during each agent invocation or allow on-demand searches via tool calls when the agent needs additional information.
 
@@ -182,7 +182,7 @@ You can write your own output by implementing and providing this callback.
 
 **Note**: If this delegate is provided, the `ContextPrompt` and `IncludeCitationsPrompt` settings will not be used.
 
-## Combining RAG with Other Providers
+## Combining GraphRAG with Other Providers
 
 The `TextSearchProvider` can be combined with other providers, such as `mem0` or `WhiteboardProvider`, to create agents with both memory and retrieval capabilities.
 
@@ -201,7 +201,7 @@ By combining these features, agents can deliver a more personalized and context-
 ## Next steps
 
 > [!div class="nextstepaction"]
-> [Explore the Agent with RAG sample](https://github.com/microsoft/semantic-kernel/blob/main/dotnet/samples/Concepts/Agents/ChatCompletion_Rag.cs)
+> [Explore the Agent with GraphRAG sample](https://github.com/microsoft/semantic-kernel/blob/main/dotnet/samples/Concepts/Agents/ChatCompletion_Rag.cs)
 
 ::: zone-end
 

semantic-kernel/concepts/vector-store-connectors/index.md

@@ -42,18 +42,18 @@ The Semantic Kernel provided imlementations are referred to as 'connectors'.
 
 ::: zone pivot="programming-language-csharp"
 
-## Retrieval Augmented Generation (RAG) with Vector Stores
+## GraphRAG with Vector Stores
 
 The vector store abstraction is a low level api for adding and retrieving data from vector stores.
-Semantic Kernel has built-in support for using any one of the Vector Store implementations for RAG.
+Semantic Kernel has built-in support for using any one of the Vector Store implementations for GraphRAG.
 This is achieved by wrapping `IVectorSearchable<TRecord>` and exposing it as a Text Search implementation.
 
 > [!TIP]
-> To learn more about how to use vector stores for RAG see [How to use Vector Stores with Semantic Kernel Text Search](../text-search/text-search-vector-stores.md).
+> To learn more about how to use vector stores for GraphRAG see [How to use Vector Stores with Semantic Kernel Text Search](../text-search/text-search-vector-stores.md).
 > [!TIP]
 > To learn more about text search see [What is Semantic Kernel Text Search?](../text-search/index.md)
 > [!TIP]
-> To learn more about how to quickly add RAG into your agent see [Adding Retrieval Augmented Generation (RAG) to Semantic Kernel Agents](../../Frameworks/agent/agent-rag.md).
+> To learn more about how to quickly add GraphRAG into your agent see [Adding GraphRAG to Semantic Kernel Agents](../../Frameworks/agent/agent-graphrag.md).
 
 ## The Vector Store Abstraction
 
@@ -81,14 +81,14 @@ Finally, the abstract base class inherits from `IVectorSearchable<TRecord>` prov
 ::: zone-end
 ::: zone pivot="programming-language-python"
 
-## Retrieval Augmented Generation (RAG) with Vector Stores
+## GraphRAG with Vector Stores
 
 The vector store abstractions are a low level api for adding and retrieving data from vector stores.
-Semantic Kernel has built-in support for using any one of the Vector Store implementations for RAG.
+Semantic Kernel has built-in support for using any one of the Vector Store implementations for GraphRAG.
 This is achieved by wrapping `VectorSearchBase[TKey, TModel]` with either `VectorizedSearchMixin[Tmodel]`, `VectorizableTextSearchMixin[TModel]` or `VectorTextSearch[TModel]` and exposing it as a Text Search implementation.
 
 > [!TIP]
-> To learn more about how to use vector stores for RAG see [How to use Vector Stores with Semantic Kernel Text Search](../text-search/text-search-vector-stores.md).
+> To learn more about how to use vector stores for GraphRAG see [How to use Vector Stores with Semantic Kernel Text Search](../text-search/text-search-vector-stores.md).
 > [!TIP]
 > To learn more about text search see [What is Semantic Kernel Text Search?](../text-search/index.md)